What are the hardware requirements for Orpheus 3B 0.1 Pretrained?

Orpheus 3B 0.1 Pretrained requires approximately 6.6 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Orpheus 3B 0.1 Pretrained and how large is it?

Orpheus 3B 0.1 Pretrained is developed by unsloth, a model with 3b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Orpheus 3B 0.1 Pretrained?

Orpheus 3B 0.1 Pretrained is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Orpheus 3B 0.1 Pretrained by unsloth — VRAM 6.6GB, 128K context

Name: Orpheus 3B 0.1 Pretrained
Author: unsloth

Orpheus 3B 0.1 Pretrained is an open-source language model by unsloth. Features: 3b LLM, VRAM: 6.6GB, Context: 128K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.18.

Base model:canopylabs/orpheus-... Base model:finetune:canopylabs... En Endpoints compatible Instruct Llama Region:us Safetensors Sharded Tensorflow Text-to-speech

Model Card on HF 🤗: https://huggingface.co/unsloth/orpheus-3b-0.1-pretrained

Orpheus 3B 0.1 Pretrained Parameters and Internals

LLM Name	Orpheus 3B 0.1 Pretrained
Repository 🤗	https://huggingface.co/unsloth/orpheus-3b-0.1-pretrained
Base Model(s)	canopylabs/orpheus-3b-0.1-pretrained meta-llama/Llama-3.2-3B-Instruct canopylabs/orpheus-3b-0.1-pretrained meta-llama/Llama-3.2-3B-Instruct
Model Size	3b
Required VRAM	6.6 GB
Updated	2026-06-05
Maintainer	unsloth
Model Type	llama
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-2 1.6 GB: 2-of-2
Supported Languages	en
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	131072
Model Max Length	131072
Transformers Version	4.51.0.dev0
Tokenizer Class	PreTrainedTokenizer
Padding Token	<\|finetune_right_pad_id\|>
Vocabulary Size	156939
Torch Data Type	bfloat16

Rank the Orpheus 3B 0.1 Pretrained capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Quantized Models of the Orpheus 3B 0.1 Pretrained

Model	Likes	Downloads	VRAM
Orpheus Cy Stage1 16bit	0	17	6 GB

Best Alternatives to Orpheus 3B 0.1 Pretrained

Best Alternatives	Context / RAM	Downloads	Likes
Llama 3.2 3B Instruct	128K / 6.5 GB	1829572	2368
Llama 3.2 3B Instruct	128K / 6.5 GB	186207	96
...3B TechWriter Instruct Unsloth	128K / 6.5 GB	6005	1
...ini Math345 GroupB Llama32 End	128K / 6.5 GB	755	0
...ama 3.2 3B TechWriter Instruct	128K / 6.4 GB	226	0
Llama 3.2 3B Instruct	128K / 6.5 GB	991	9
HyLo Llama 6MLA22GDN 8K SFT	128K / 17.1 GB	42	1
Alloma 3B Instruct	128K / 6.5 GB	55456	6
Llama3.2 3B Manumit V1	128K / 6.4 GB	135	0
... V7 SFT 10voicebot Loopcleaned	128K / 6.5 GB	229	0

Note: green Score (e.g. "73.2") means that the model is better than unsloth/orpheus-3b-0.1-pretrained.